AL-BaseModel

BaseModel.py

class BaseModel(object):

    def __init__(self):
        pass

    def fit_predict(self):
        pass


class SvmModel(BaseModel):

    model_type = 'Support Vector Machine with linear Kernel'
    def fit_predict(self, X_train, y_train, X_val, X_test, c_weight):
        print ('training svm...')
        self.classifier = SVC(C=1, kernel='linear', probability=True,
                              class_weight=c_weight)
        self.classifier.fit(X_train, y_train)
        self.test_y_predicted = self.classifier.predict(X_test)
        self.val_y_predicted = self.classifier.predict(X_val)
        return (X_train, X_val, X_test, self.val_y_predicted,
                self.test_y_predicted)


class LogModel(BaseModel):

    model_type = 'Multinominal Logistic Regression' 
    
    def fit_predict(self, X_train, y_train, X_val, X_test, c_weight):
        print ('training multinomial logistic regression')
        train_samples = X_train.shape[0]
        self.classifier = LogisticRegression(
            C=50. / train_samples,
            multi_class='multinomial',
            penalty='l1',
            solver='saga',
            tol=0.1,
            class_weight=c_weight,
            )
        self.classifier.fit(X_train, y_train)
        self.test_y_predicted = self.classifier.predict(X_test)
        self.val_y_predicted = self.classifier.predict(X_val)
        return (X_train, X_val, X_test, self.val_y_predicted,
                self.test_y_predicted)

class RfModel(BaseModel):

    model_type = 'Random Forest'
    
    def fit_predict(self, X_train, y_train, X_val, X_test, c_weight):
        print ('training random forest...')
        self.classifier = RandomForestClassifier(n_estimators=500, class_weight=c_weight)
        self.classifier.fit(X_train, y_train)
        self.test_y_predicted = self.classifier.predict(X_test)
        self.val_y_predicted = self.classifier.predict(X_val)
        return (X_train, X_val, X_test, self.val_y_predicted, self.test_y_predicted)